get_decision_text

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint and idempotentHint, which describe safe read behavior. However, the description adds crucial behavioral detail: 'full=false(기본) 시 본문 계단식 축약' (full=false(default) shows cascading text abbreviation). This explains the tool's key behavioral nuance beyond the boolean parameter schema, such as why certain sections like 판시·요지·주문 are always full regardless. The description also notes it covers '18개 도메인' (18 domains), which contextualizes the scope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two fragments totaling about 20 words. It front-loads the tool's purpose ('18개 도메인 전문 조회') and immediately follows with required parameters, then the key behavioral switch. Every word carries meaning, and there is no redundancy with annotations or schema. This is exemplary conciseness for a multilingual context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that the tool has 4 parameters (2 required), 100% schema coverage, and no output schema, the description provides the necessary context: domain list origin (search results for id), full mode explanation, and domain-specific options example. The description is complete for triggering invocation, detailing the core conditional behavior that influences the response format, despite the lack of output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, meaning all 4 parameters have descriptions. The description does not repeat parameter names but adds meaningful context: id comes from search results, full mode defaults to false with abbreviated text, and the domain enum covers 18 domains. Additionally, the description provides example usage for options, clarifying that it's a domain-specific map. This demonstrates high value beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as a comprehensive query tool for Korean legal decisions across 18 domains, requiring domain and id. The verb is implied ('조회' = lookup/query), and the resource is decision text. It distinguishes itself from sibling tools like search_law (search) and get_law_text (different text endpoint) by specifying domain and id structure. The Korean-Konglish naming convention and contents are clear for a Korean-law-targeted agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly tells when to use this tool: when you have a specific domain and id (likely from search results) and need decision text. It includes how to get full vs abbreviated text via the full parameter. However, it does not explicitly state when NOT to use it or which sibling tool to use instead—e.g., use search_decisions when you don't have an id, or query with options first. This is a minor gap for a tool with complex domain structure.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.